【机器学习100天】多元线性回归 | 第3天

第三天：多元线性回归

下面是完整的代码：

#Step 1: Data Preprocessing 数据预处理
import pandas as pd
import numpy as np

dataset = pd.read_csv('C:\\Users\\Amanda\\Desktop\\python\\ML-Learning\\datasets\\50_Startups.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[:,4].values
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
labelencoder = LabelEncoder()
X[:,3] = labelencoder.fit_transform(X[:,3])

from sklearn.compose import ColumnTransformer
ct = ColumnTransformer(transformers=[('State', OneHotEncoder(), [3])])
X = ct.fit_transform(X)
X = X[:,1:]

#from sklearn.cross_validation import train_test_split
#ModuleNotFoundError: No module named 'sklearn.cross_validation'
from sklearn.model_selection import train_test_split
X_train,X_test,Y_train,Y_test = train_test_split(X,Y,test_size = 0.2, random_state=0)

# Step 2: Fitting Multiple Linear Regression to the Training set 将多个线性回归拟合到训练集
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, Y_train)
y_pred = regressor.predict(X_test)